INDEX

Explanations

references to standard questions or prompts within specific contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 knex

-0.54

Vegeu

-0.51

RTGC

-0.49

AppMethodBeat

-0.48

QtCore

-0.48

plish

-0.47

Technik

-0.47

 cross

-0.46

AccessFile

-0.44

ussure

-0.44

POSITIVE LOGITS

 الحره

0.81

 bezeichneter

0.79

</thead>

0.71

出版年

0.70

Koordinaten

0.67

发表于

0.64

ymce

0.63

Datuak

0.63

0.62

******/

0.61

Activations Density 0.013%

references to standard questions or prompts within specific contexts

No Comments

No Known Activations